|
| 1 | +import requests |
| 2 | + |
| 3 | +from bs4 |
| 4 | +import BeautifulSoup |
| 5 | + |
| 6 | +print('Enter movie/Tv series name') |
| 7 | + |
| 8 | +movie = input() |
| 9 | + |
| 10 | +print() |
| 11 | + |
| 12 | +url = 'http://www.imdb.com/find?ref_=nv_sr_fn&q=' + movie + '&s=all' |
| 13 | + |
| 14 | +def get_title(movie_url): |
| 15 | + |
| 16 | + source_code = requests.get(movie_url) |
| 17 | + |
| 18 | +plain_text = source_code.text |
| 19 | + |
| 20 | +soup = BeautifulSoup(plain_text, 'lxml') |
| 21 | + |
| 22 | +for title in soup.findAll('div', { |
| 23 | + 'class': 'title_wrapper' |
| 24 | + }): |
| 25 | + |
| 26 | + return title.find('h1').text.rstrip() |
| 27 | + |
| 28 | +source_code = requests.get(url) |
| 29 | + |
| 30 | +plain_text = source_code.text |
| 31 | + |
| 32 | +soup = BeautifulSoup(plain_text, 'lxml') |
| 33 | + |
| 34 | +for td in soup.findAll('td', { |
| 35 | + 'class': 'result_text' |
| 36 | + }): |
| 37 | + |
| 38 | + href = td.find('a')['href'] |
| 39 | + |
| 40 | +movie_page = 'http://www.imdb.com' + href |
| 41 | + |
| 42 | +break |
| 43 | + |
| 44 | +movie_name = get_title(movie_page) |
| 45 | + |
| 46 | +def get_movie_data(movie_url): |
| 47 | + |
| 48 | + source_code = requests.get(movie_url) |
| 49 | + |
| 50 | +plain_text = source_code.text |
| 51 | + |
| 52 | +soup = BeautifulSoup(plain_text, 'lxml') |
| 53 | + |
| 54 | +for div in soup.findAll('div', { |
| 55 | + 'class': 'ratingValue' |
| 56 | + }): |
| 57 | + |
| 58 | + print('Imdb rating of the movie/Tv Series "' + movie_name + '" is: ', end = '') |
| 59 | + |
| 60 | +print(div.text) |
| 61 | + |
| 62 | +print() |
| 63 | + |
| 64 | +for div in soup.findAll('div', { |
| 65 | + 'class': 'summary_text' |
| 66 | + }): |
| 67 | + |
| 68 | + print('Summary of the movie/Tv series:') |
| 69 | + |
| 70 | +print(div.text.lstrip()) |
| 71 | + |
| 72 | +get_movie_data(movie_page) |
| 73 | + |
| 74 | +'' |
| 75 | +'print_genre = soup.findAll(' |
| 76 | +div ',{' |
| 77 | +class ':' |
| 78 | +subtext '}) |
| 79 | + |
| 80 | +for div in print_genre: |
| 81 | + |
| 82 | + for genre in print_genre.findAll('a'): |
| 83 | + |
| 84 | + print(genre.text, end = ' |') |
| 85 | + |
| 86 | +print() |
| 87 | +'' |
| 88 | +' |
0 commit comments